Idle Energy

CoWirshing - 05/05/2026 -

Currently working on this game. I had wanted to release this game by now but I keep hitting minor walls.

Once I knew AI was capable of creating games, the plan was to generate another game quickly to learn more about the AI's capabilities. Unfortunately, I hit three major issues right out of the gate: selecting a type of game I could easily understand and design for, learning how to direct the AI to make that type of game, and efficiently using the AI to code.

Initially I attempted to make a pinball game because it seemed simple enough. The need for a physics engine complicated the matter and I'm not willing to install a game engine until I know I will absolutely need one for these projects. I spent several days researching the best types of games I should focus on being limited to HTML, which is how I ended up on the Idle Game genera. The genera is not one I have spent much time playing so I spent the next few days learning about the different types of idle games, their origins, mechanics, and settling on a model that would be simple to implement.

I thought directing the AI to make a simple idle game would have been swift and easy. The initial idea of 'Clicking' and 'Gaining' a resource was easy to code, but then we needed to do something with that resource to add a reason to collect the resource. Surveying the landscape of idle games, I couldn't find one that dealt with energy generation. So, we have a resource and we can spend that to create ways of auto-generating the resource, introducing the idea of power plants. This idea led to different eras of power generation, which lead to needing energy to scale up exponentially. Ultimately, spending energy for energy producers didn't make a ton of sense, so currency was introduced as a second resource, followed by the need to generate literal resources (wood, metal, microchips, etc.). As the game ballooned, directing the AI efficiently became increasingly more difficult, as terms within the initial game design were not well defined. This is a core issue with vibe coding, a lack of structure that can make changes or introduction of new features more difficult as development goes on.

As the game formed and grew in scope, so did the token consumption of Claude. Making good, thoughtful changes in an efficient way, and correcting misunderstandings caused by my assumptions and poor wording, was eating a lot of data and processing power. When using an AI that is token capped, like Claude, unnecessary token consumption turns development into a slog. The advantage of AI is quick testing, changes, and iteration, so constantly reaching the hourly and weekly caps has slowed progress immensely, removing that advantage entirely. The solution is simple, but not one I can employ at this stage for the current game.

For the next game, I will need AI agents and skills to maintain efficiency in order to maximize the potential of using AIs to create games. These aspects of using AI should reduce the unnecessary token expenditure, returning me to the expect pace of development.

CoWirshing - 05/20/2026 -

This game has taken way longer then I thought...

First, interating the different changes in a timely manner has required a more powerful version of the AI, meaning higher costs.

Second, now I have to figure out how to package the game and make it suitable for both Windows and Android. For now, Macs are out of my reach.

Third, I need to figure out how the Steam release process works. Then actually go through the 2 week release process of Google testing and approval again.

The only silver lining is, having access to a stronger AI as a consiquence to all the needs. I can use it to help teach me what to do, how to navigate these extrnal systems, and how to update the copy so that the games can connect to Google's and Steam's achivement systems.

CoWirshing - 05/28/2026 -

There are still so many aspect to using the AI tools that I never considered. Learning everything needed to make this game as been a humbling experience: the genera of game, the coding and AI models, the different types of AI needed, the vast array of tools each has to offer, the individual prompt techniques needed for each, then blending all of them together. Finally, I think I am in the home stretch. Only tasks left are music and to learn how to release the game into Steam. I doubt these will be as easy I am hoping they are, so the game could still be a few weeks out from this point.

CoWirshing - 06/03/2026 -

After a painful amount of review, adjustment, and copy creation, I can firmly say the end of the tunnel is here. Game is complete. Testing can begin. Though the connection to Steam is still in progress. This was a much more difficult challenge then the 1st game.

This game helped create processes and flows that will be nessissary when building out more complex games, especially as these works start to involve more people. A colabritive effort should take far less time, even if the complexity is significantly greater. All the lessons learned and problems solved have provided a massive return in the form of experience.

CoWirshing - 06/07/2026 -

The game is done. Testing has started, can so has the long, painful process of releasing it on Steam. As part of all of this, I considered tackling the challenge of setting up an LLC for the Studio, though that would have dragged out the release process even further. To not delay any further, it is simply being released under my own Steam name since I am the sole human contributor to the game. The next project, which will have several of us participating, will require a formal Studio structure. That process is not a fast one either, but I will have more time to learn and tackle it while we work through the idea and design phase.

As for Idle Energy, a lot of lessons were learned which will help make our 1st polished project much better then it otherwise would have been.

If you wish to support our ideas, games, and missions, please consider purchasing the games on their available platforms. If you wish to contribute without purchasing, we will plan on setting up a patron backing and social media content soon.

CoWirshing - 06/26/2026 -

Been a while since an update. Short version is 'Release Hell'. Steam as a ton of small requirements and particular assets that need to be created, uploaded, and approved before a game can be released. Ironic enough, the game has been approved but the related store entry has not. Most of this is due to a transparency issue with a few of the image assets. Since the logos were created without transparency in mind, there is no time-efficient way to accomplish this. Three review cycles in and we have a single asset holding up the review.

On a positive note, this 'waiting around' has allowed me to start to expand upon the Studio structures. We have a Discord (communication), Patreon (studio support and sale of game related assets), additional studio participants (about section), and formal company / studio documentation now in the works. Our current goal is to build a structure and learn the tools to make a polished game next, something more than just proof of concept. Exactly what this is has not been fully solidified, but there is adjacent development going on in the background while we wait for this game to be released.

If you want to support us, we have a 'Support Our Mission' section. We plan on expanding our social media presence soon as well from there.

Page updated

Google Sites

Report abuse